© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 1519
    Prev
    Next
    INDEX
    Explanations

    mathematical notations, particularly fractions, sums, and symbols used in scientific and mathematical expressions.

    oai_token-act-pair · gemini-2.0-flash

    mathematical equations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <
    -1.01
    “
    -0.98
    WithIOException
    -0.98
    &
    -0.91
    [
    -0.85
    \"
    -0.82
    ”
    -0.81
    \\
    -0.78
    ~
    -0.74
    OGND
    -0.73
    POSITIVE LOGITS
    ært
    0.50
    zuführen
    0.49
    ╠
    0.46
    ัติ
    0.45
    śred
    0.45
    噙
    0.44
    ობ
    0.44
    '">
    0.43
    citenamefont
    0.43
    }");
    0.43
    Activations Density 9.963%

    No Known Activations